THU-LYJ-Lab/O2-Recon
[AAAI 2024] O2-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model
This project helps create complete 3D models of objects, even when parts of them are hidden or out of view in camera images. It takes 2D images where objects might be occluded and produces a full 3D surface reconstruction of those objects. This tool is for researchers and practitioners working in computer vision, robotics, or augmented reality who need accurate 3D representations from imperfect real-world scans.
No commits in the last 6 months.
Use this if you need to generate a complete 3D model of an object from multiple 2D images, especially when parts of the object are consistently obscured across different views.
Not ideal if your primary goal is to reconstruct entire scenes rather than individual, occluded objects, or if you only have a single 2D image without depth information.
Stars
26
Forks
1
Language
Python
License
—
Category
Last pushed
Nov 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/THU-LYJ-Lab/O2-Recon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...